This is a LoRA trained on muddy faces, hair and bodies with various levels of sinking into quicksand or mud. What it does is provide extreme mud coverage and color control. Base models give you small mud splatters that are always brown, whereas this can make 100% covered or made of mud body parts and clothing in the color of your choice. The quicksand is more a side effect of the main target, but I think it is an improvement overall.Recommended strength is 1. Consider lowering CFG to improve quality before modifying LoRA strength, I used CFG 4. Trained trigger words are: muddy face, muddy head, muddy body, brown mud, grey mud, light mud, dark mud, black mud, orange mud, green mud, quicksand, thigh-deep, waist-deep, chest-deep, shoulder-deep, neck-deep, mouth-deep.It can generate colors other than trained ones, such as red, blue, pink or yellow. I recommend omitting 'monochrome' and 'greyscale' from negatives if you are making black or grey mud, and making sure to include them with colorful mud.When making quicksand scenes, I typically got better results pairing 'quicksand' with 'close-up', 'portrait', 'upper body', etc. instead of using the 'x-deep' tags, but they can still sometimes help reinforce the concept.This is NOT designed for realism. In my tests I got okay results with Pony Realism, but it is not the focus of this LoRA.If you like what this can do, please take a moment to post an image to this model, it helps me out a lot. Thank you!
